Add library_name

LICENSE

@@ -1,9 +0,0 @@
-MIT License
-Copyright (c) 2025 Nvidia
-Copyright (c) 2023 DeepSeek
-
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -1,8 +1,8 @@
 ---
-pipeline_tag: text-generation
 base_model:
 - deepseek-ai/DeepSeek-R1
-license: mit
+pipeline_tag: text-generation
+library_name: transformers
 ---
 # Model Overview
 
@@ -15,7 +15,7 @@ This model is ready for commercial/non-commercial use.  <br>
 This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA [(DeepSeek R1) Model Card](https://huggingface.co/deepseek-ai/DeepSeek-R1).
 
 ### License/Terms of Use:
-[MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md)
+[nvidia-open-model-license](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/)
 
 
 ## Model Architecture:
@@ -25,18 +25,18 @@ This model is not owned or developed by NVIDIA. This model has been developed an
 ## Input:
 **Input Type(s):** Text <br>
 **Input Format(s):** String <br>
-**Input Parameters:** One Dimensional(1D): Sequences <br>
+**Input Parameters:** 1D (One Dimensional): Sequences <br>
 **Other Properties Related to Input:** Context length up to 128K <br>
 
 ## Output:
 **Output Type(s):** Text <br>
 **Output Format:** String <br>
-**Output Parameters:** 1D: Sequences <br>
+**Output Parameters:** 1D (One Dimensional): Sequences <br>
 **Other Properties Related to Output:** N/A <br>
 
 ## Software Integration:
 **Supported Runtime Engine(s):** <br>
-* TensorRT-LLM <br>
+* Tensor(RT)-LLM <br>
 
 **Supported Hardware Microarchitecture Compatibility:** <br>
 * NVIDIA Blackwell <br>
@@ -57,7 +57,7 @@ The model is quantized with nvidia-modelopt **v0.23.0**  <br>
 
 
 ## Inference:
-**Engine:** TensorRT-LLM <br>
+**Engine:** Tensor(RT)-LLM <br>
 **Test Hardware:** B200 <br>
 
 ## Post Training Quantization
@@ -101,53 +101,6 @@ if __name__ == '__main__':
 
 ```
 
-### Evaluation
-The accuracy benchmark results are presented in the table below:
-<table>
-  <tr>
-   <td><strong>Precision</strong>
-   </td>
-   <td><strong>MMLU</strong>
-   </td>
-   <td><strong>GSM8K</strong>
-   </td>
-   <td><strong>AIME2024</strong>
-   </td>
-   <td><strong>GPQA Diamond</strong>
-   </td>
-   <td><strong>MATH-500</strong>
-   </td>
-  </tr>
-  <tr>
-   <td>FP8
-   </td>
-   <td>90.8
-   </td>
-   <td>96.3
-   </td>
-   <td>80.0
-   </td>
-   <td>69.7
-   </td>
-   <td>95.4
-   </td>
-  </tr>
-  <tr>
-   <td>FP4
-   </td>
-   <td>90.7
-   </td>
-   <td>96.1
-   </td>
-   <td>80.0
-   </td>
-   <td>69.2
-   </td>
-   <td>94.2
-   </td>
-  </tr>
-  <tr>
-</table>
 
 ## Ethical Considerations
 

config.json

@@ -36,6 +36,15 @@
   "q_lora_rank": 1536,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "beta_fast": 32,